From e02bb91e0eb8a43b38a363b1de3238a36d92d82c Mon Sep 17 00:00:00 2001 From: team mradermacher Date: Mon, 20 Jan 2025 08:47:02 +0000 Subject: [PATCH] auto-patch README.md --- README.md | 72 +++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 72 insertions(+) diff --git a/README.md b/README.md index 02225e0..92d12bf 100644 --- a/README.md +++ b/README.md @@ -1,6 +1,78 @@ +--- +base_model: CultriX/Qwen2.5-14B-Hyper +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + weighted/imatrix quants of https://huggingface.co/CultriX/Qwen2.5-14B-Hyper + + +static quants are available at https://huggingface.co/mradermacher/Qwen2.5-14B-Hyper-GGUF +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Hyper-i1-GGUF/resolve/main/Qwen2.5-14B-Hyper.i1-IQ1_S.gguf) | i1-IQ1_S | 3.7 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Hyper-i1-GGUF/resolve/main/Qwen2.5-14B-Hyper.i1-IQ1_M.gguf) | i1-IQ1_M | 4.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Hyper-i1-GGUF/resolve/main/Qwen2.5-14B-Hyper.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Hyper-i1-GGUF/resolve/main/Qwen2.5-14B-Hyper.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Hyper-i1-GGUF/resolve/main/Qwen2.5-14B-Hyper.i1-IQ2_S.gguf) | i1-IQ2_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Hyper-i1-GGUF/resolve/main/Qwen2.5-14B-Hyper.i1-IQ2_M.gguf) | i1-IQ2_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Hyper-i1-GGUF/resolve/main/Qwen2.5-14B-Hyper.i1-Q2_K_S.gguf) | i1-Q2_K_S | 5.5 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Hyper-i1-GGUF/resolve/main/Qwen2.5-14B-Hyper.i1-Q2_K.gguf) | i1-Q2_K | 5.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Hyper-i1-GGUF/resolve/main/Qwen2.5-14B-Hyper.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 6.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Hyper-i1-GGUF/resolve/main/Qwen2.5-14B-Hyper.i1-IQ3_XS.gguf) | i1-IQ3_XS | 6.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Hyper-i1-GGUF/resolve/main/Qwen2.5-14B-Hyper.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Hyper-i1-GGUF/resolve/main/Qwen2.5-14B-Hyper.i1-IQ3_S.gguf) | i1-IQ3_S | 6.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Hyper-i1-GGUF/resolve/main/Qwen2.5-14B-Hyper.i1-IQ3_M.gguf) | i1-IQ3_M | 7.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Hyper-i1-GGUF/resolve/main/Qwen2.5-14B-Hyper.i1-Q3_K_M.gguf) | i1-Q3_K_M | 7.4 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Hyper-i1-GGUF/resolve/main/Qwen2.5-14B-Hyper.i1-Q3_K_L.gguf) | i1-Q3_K_L | 8.0 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Hyper-i1-GGUF/resolve/main/Qwen2.5-14B-Hyper.i1-IQ4_XS.gguf) | i1-IQ4_XS | 8.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Hyper-i1-GGUF/resolve/main/Qwen2.5-14B-Hyper.i1-Q4_0.gguf) | i1-Q4_0 | 8.6 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Hyper-i1-GGUF/resolve/main/Qwen2.5-14B-Hyper.i1-IQ4_NL.gguf) | i1-IQ4_NL | 8.6 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Hyper-i1-GGUF/resolve/main/Qwen2.5-14B-Hyper.i1-Q4_K_S.gguf) | i1-Q4_K_S | 8.7 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Hyper-i1-GGUF/resolve/main/Qwen2.5-14B-Hyper.i1-Q4_K_M.gguf) | i1-Q4_K_M | 9.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Hyper-i1-GGUF/resolve/main/Qwen2.5-14B-Hyper.i1-Q4_1.gguf) | i1-Q4_1 | 9.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Hyper-i1-GGUF/resolve/main/Qwen2.5-14B-Hyper.i1-Q5_K_S.gguf) | i1-Q5_K_S | 10.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Hyper-i1-GGUF/resolve/main/Qwen2.5-14B-Hyper.i1-Q5_K_M.gguf) | i1-Q5_K_M | 10.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Hyper-i1-GGUF/resolve/main/Qwen2.5-14B-Hyper.i1-Q6_K.gguf) | i1-Q6_K | 12.2 | practically like static Q6_K | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +